基于花朵授粉优化极限学习机的高炉铁水硅含量预测

在高炉冶炼过程中,铁水硅含量是反映高炉炉内温度的重要参数之一,通过对铁水硅含量变化趋势进行预测分析,为后续高炉参数调整提供理论依据。针对铁水硅含量数据的非线性特点,提出基于花朵授粉算法的极限学习机预测方法。利用花朵授粉算法优化极限学习机参数,并通过优化后的极限学习机算法构建铁水硅含量的预测模型,以某钢铁厂生产数据作为验证。仿真结果表明,相较于传统预测方法,该预测模型在预测精度以及泛化能力均有所提高,具有良好的稳定性。

Prediction of hot metal silicon content in blast furnace based on extreme learning machine and flower pollinate algorithm

In smelting process of blast furnace, silicon content in hot metal is one of the main parameters to reflect the thermal condition inside the blast furnace. By predicting and analyzing the silicon content in hot metal, the theoretical basis for subsequent parameters adjustment is provided. Aiming at the non-linear feature of hot metal silicon content, a prediction method based on extreme learning machine and flower pollinate algorithm is proposed. Flower pollinate algorithm is applied to optimize the parameters of extreme learning machine, and the prediction model of silicon content is constructed by optimized extreme learning machine. Verified with the production data of a steelworks, the simulation results show that compared with the traditional prediction method, the proposed prediction model speeds up the prediction accuracy and generalization ability, and it also has good stability.